Toward robust mammography-based models for breast cancer risk

Improved breast cancer risk models enable targeted screening strategies that achieve earlier detection and less screening harm than existing guidelines. To bring deep learning risk models to clinical practice, we need to further refine their accuracy, validate them across diverse populations, and de...

Full description

Saved in:
Bibliographic Details
Published in:Science translational medicine 2021-01, Vol.13 (578), p.eaba4373
Main Authors: Yala, Adam, Mikhael, Peter G, Strand, Fredrik, Lin, Gigin, Smith, Kevin, Wan, Yung-Liang, Lamb, Leslie, Hughes, Kevin, Lehman, Constance, Barzilay, Regina
Format: Article
Language:English
Subjects:
Breast cancer
Deep learning
Mammography
Medicin och hälsovetenskap
Patients
Risk factors
Risk groups
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Improved breast cancer risk models enable targeted screening strategies that achieve earlier detection and less screening harm than existing guidelines. To bring deep learning risk models to clinical practice, we need to further refine their accuracy, validate them across diverse populations, and demonstrate their potential to improve clinical workflows. We developed Mirai, a mammography-based deep learning model designed to predict risk at multiple timepoints, leverage potentially missing risk factor information, and produce predictions that are consistent across mammography machines. Mirai was trained on a large dataset from Massachusetts General Hospital (MGH) in the United States and tested on held-out test sets from MGH, Karolinska University Hospital in Sweden, and Chang Gung Memorial Hospital (CGMH) in Taiwan, obtaining C-indices of 0.76 (95% confidence interval, 0.74 to 0.80), 0.81 (0.79 to 0.82), and 0.79 (0.79 to 0.83), respectively. Mirai obtained significantly higher 5-year ROC AUCs than the Tyrer-Cuzick model ( < 0.001) and prior deep learning models Hybrid DL ( < 0.001) and Image-Only DL ( < 0.001), trained on the same dataset. Mirai more accurately identified high-risk patients than prior methods across all datasets. On the MGH test set, 41.5% (34.4 to 48.5) of patients who would develop cancer within 5 years were identified as high risk, compared with 36.1% (29.1 to 42.9) by Hybrid DL ( = 0.02) and 22.9% (15.9 to 29.6) by the Tyrer-Cuzick model ( < 0.001).
ISSN:1946-6234
1946-6242
1946-6242
1946-3242
DOI:10.1126/scitranslmed.aba4373